Wei Deng created CASSANDRA-11694:
------------------------------------
Summary: sstabledump doesn't represent static columns correctly
Key: CASSANDRA-11694
URL: https://issues.apache.org/jira/browse/CASSANDRA-11694
Project: Cassandra
Issue Type: Bug
Components: Tools
Reporter: Wei Deng
It appears that the latest trunk code (after fixing CASSANDRA-11654,
CASSANDRA-11655 and CASSANDRA-11656) of sstabledump still doesn't handle static
columns correctly.
Take a look at the following example:
{noformat}
root@node0:/mnt/ephemeral/cassandra/data/testks/test_static_column-ab5ce7c20b8411e695aeebb3bfdd5790#
~/cassandra-trunk/tools/bin/sstabledump ma-1-big-Data.db -t
[
{
"partition" : {
"key" : [ "1" ],
"position" : 0
},
"rows" : [
{
"type" : "static_block",
"position" : 40,
"cells" : [
{ "name" : "static0_int", "value" : "3000", "tstamp" :
"1461657675565767" },
{ "name" : "static1_int", "value" : "4000", "tstamp" :
"1461657675565767" }
]
},
{
"type" : "row",
"position" : 40,
"clustering" : [ "c1" ],
"liveness_info" : { "tstamp" : "1461657663393419" },
"cells" : [
{ "name" : "val0_int", "value" : "100" },
{ "name" : "val1_set_of_int", "deletion_info" : { "marked_deleted" :
"1461657663393418", "local_delete_time" : "1461657663" } },
{ "name" : "val1_set_of_int", "path" : [ "1" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "2" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "3" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "4" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "5" ], "value" : "" }
]
},
{
"type" : "row",
"position" : 92,
"clustering" : [ "c2" ],
"liveness_info" : { "tstamp" : "1461657675565767" },
"cells" : [
{ "name" : "val0_int", "value" : "200" },
{ "name" : "val1_set_of_int", "deletion_info" : { "marked_deleted" :
"1461657675565766", "local_delete_time" : "1461657675" } },
{ "name" : "val1_set_of_int", "path" : [ "1" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "2" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "3" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "4" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "5" ], "value" : "" }
]
},
{
"type" : "row",
"position" : 144,
"clustering" : [ "c3" ],
"liveness_info" : { "tstamp" : "1461657634639043" },
"cells" : [
{ "name" : "val0_int", "value" : "300" },
{ "name" : "val1_set_of_int", "deletion_info" : { "marked_deleted" :
"1461657634639042", "local_delete_time" : "1461657634" } },
{ "name" : "val1_set_of_int", "path" : [ "1" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "2" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "3" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "4" ], "value" : "" },
{ "name" : "val1_set_of_int", "path" : [ "5" ], "value" : "" }
]
}
]
}
]
{noformat}
Note the "position" for the "static_block" and the first "row" are the same
(40), which should be incorrect.
If you print out in debug mode, you will see the following:
{noformat}
root@node0:/mnt/ephemeral/cassandra/data/testks/test_static_column-ab5ce7c20b8411e695aeebb3bfdd5790#
~/cassandra-trunk/tools/bin/sstabledump ma-1-big-Data.db -t -d
[1]@0 Row[info=[ts=-9223372036854775808] ]: STATIC | [static0_int=3000
ts=1461657675565767], [static1_int=4000 ts=1461657675565767]
[1]@0 Row[info=[ts=1461657663393419] ]: c1 | [val0_int=100
ts=1461657663393419], del(val1_set_of_int)=deletedAt=1461657663393418,
localDeletion=1461657663, [val1_set_of_int[1]= ts=1461657663393419],
[val1_set_of_int[2]= ts=1461657663393419], [val1_set_of_int[3]=
ts=1461657663393419], [val1_set_of_int[4]= ts=1461657663393419],
[val1_set_of_int[5]= ts=1461657663393419]
[1]@92 Row[info=[ts=1461657675565767] ]: c2 | [val0_int=200
ts=1461657675565767], del(val1_set_of_int)=deletedAt=1461657675565766,
localDeletion=1461657675, [val1_set_of_int[1]= ts=1461657675565767],
[val1_set_of_int[2]= ts=1461657675565767], [val1_set_of_int[3]=
ts=1461657675565767], [val1_set_of_int[4]= ts=1461657675565767],
[val1_set_of_int[5]= ts=1461657675565767]
[1]@144 Row[info=[ts=1461657634639043] ]: c3 | [val0_int=300
ts=1461657634639043], del(val1_set_of_int)=deletedAt=1461657634639042,
localDeletion=1461657634, [val1_set_of_int[1]= ts=1461657634639043],
[val1_set_of_int[2]= ts=1461657634639043], [val1_set_of_int[3]=
ts=1461657634639043], [val1_set_of_int[4]= ts=1461657634639043],
[val1_set_of_int[5]= ts=1461657634639043]
{noformat}
There are three problems in this "-d" output:
1. It printed an invalid timestamp "ts=-9223372036854775808".
2. It printed "@0" twice at the beginning, which should be impossible.
3. It doesn't print "CellPath" component for the collection, which is
important, collection type like "set" will only put its element in the Cell
Path so if you don't print that you're missing some information in the output.
So there are a total of four issues we need to fix when dealing with static
columns.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
